From 5597613fb3cf0e36d26cfd8fb2a63196da249333 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 24 May 2024 18:30:56 +0200
Subject: [PATCH] selftests: mptcp: lib: support flaky subtests

Some subtests can be unstable, failing once every X runs. Fixing them
can take time: there could be an issue in the kernel or in the subtest,
and it is then important to do a proper analysis, not to hide real bugs.

To avoid creating noises on the different CIs, it is important to have a
simple way to mark subtests as flaky, and ignore the errors. This is
what this patch introduces: subtests can be marked as flaky by setting
MPTCP_LIB_SUBTEST_FLAKY env var to 1, e.g.

  MPTCP_LIB_SUBTEST_FLAKY=1 <run flaky subtest>

The subtest will be executed, and errors (if any) will be ignored. It is
still good to run these subtests, as it exercises code, and the results
can still be useful for the on-going investigations.

Note that the MPTCP CI will continue to track these flaky subtests by
setting SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var to 1, and a ticket
has to be created before marking subtests as flaky.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240524-upstream-net-20240524-selftests-mptcp-flaky-v1-1-a352362f3f8e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_lib.sh  | 30 +++++++++++++++++--
 1 file changed, 28 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index ad2ebda5cb64..6ffa9b7a3260 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -21,6 +21,7 @@ declare -rx MPTCP_LIB_AF_INET6=10
 
 MPTCP_LIB_SUBTESTS=()
 MPTCP_LIB_SUBTESTS_DUPLICATED=0
+MPTCP_LIB_SUBTEST_FLAKY=0
 MPTCP_LIB_TEST_COUNTER=0
 MPTCP_LIB_TEST_FORMAT="%02u %-50s"
 MPTCP_LIB_IP_MPTCP=0
@@ -41,6 +42,16 @@ else
 	readonly MPTCP_LIB_COLOR_RESET=
 fi
 
+# SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var can be set not to ignore errors
+# from subtests marked as flaky
+mptcp_lib_override_flaky() {
+	[ "${SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY:-}" = 1 ]
+}
+
+mptcp_lib_subtest_is_flaky() {
+	[ "${MPTCP_LIB_SUBTEST_FLAKY}" = 1 ] && ! mptcp_lib_override_flaky
+}
+
 # $1: color, $2: text
 mptcp_lib_print_color() {
 	echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}"
@@ -72,7 +83,16 @@ mptcp_lib_pr_skip() {
 }
 
 mptcp_lib_pr_fail() {
-	mptcp_lib_print_err "[FAIL]${1:+ ${*}}"
+	local title cmt
+
+	if mptcp_lib_subtest_is_flaky; then
+		title="IGNO"
+		cmt=" (flaky)"
+	else
+		title="FAIL"
+	fi
+
+	mptcp_lib_print_err "[${title}]${cmt}${1:+ ${*}}"
 }
 
 mptcp_lib_pr_info() {
@@ -208,7 +228,13 @@ mptcp_lib_result_pass() {
 
 # $1: test name
 mptcp_lib_result_fail() {
-	__mptcp_lib_result_add "not ok" "${1}"
+	if mptcp_lib_subtest_is_flaky; then
+		# It might sound better to use 'not ok # TODO' or 'ok # SKIP',
+		# but some CIs don't understand 'TODO' and treat SKIP as errors.
+		__mptcp_lib_result_add "ok" "${1} # IGNORE Flaky"
+	else
+		__mptcp_lib_result_add "not ok" "${1}"
+	fi
 }
 
 # $1: test name